'RP-Live Wire Algorithms'

摘要

In this paper, texture segmentation algorithm is proposed to partition the complex aerial insulator images into sub-regions with closed smooth contours. Firstly, Gray Level Co-occurrence Matrix (GLCM) is employed to extract the texture features of insulators and is calculated by the rapid Gray Level Co-occurrence Integrated Algorithm (GLCIA). We divide the extracted texture features into two categories: one with the stronger discriminative ability and the other with weaker ability. The second category is optimized by Random Projection to better distinguish the different the different texture object with low contrast. For segmentation live wire algorithm is used. The Experimental result on synthetic & real aerial insulator remote sensing images have shown that the proposed algorithm obtains more satisfactory segmentation compared to the classical models in terms of accuracy, efficiency and fast. The influence of the algorithm parameters is also analyzed.